© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 5377
    Prev
    Next
    INDEX
    Explanations

    specific formatting or stylistic elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    378
    +0.12
    0.5%
    344
    +0.10
    0.5%
    422
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.12
    0.02
    739
    +0.10
    0.01
    42
    +0.10
    0.01
    Negative Logits
    draft
    -0.71
    ministic
    -0.68
    uce
    -0.68
     overfl
    -0.66
    isp
    -0.65
    akening
    -0.65
    anship
    -0.64
    erd
    -0.64
    ucer
    -0.64
    hemer
    -0.64
    POSITIVE LOGITS
    "]=>
    1.11
     ["
    1.00
     Whilst
    0.75
     Monica
    0.71
     Rih
    0.71
    */(
    0.70
     partName
    0.69
     </
    0.66
     Played
    0.65
     haha
    0.65
    Activations Density 0.041%

    No Known Activations